This article presents automated methods and tools for lexicographic research and dictionary development for Bengali Sign Language (BdSL). The research addresses the challenge of documenting BdSL, an under-resourced sign language primarily used in Bangladesh and Indian Bengali-speaking regions. Established lexicographic methods require extensive manual effort to capture the multidimensional features of signs, including handshape, location, movement, orientation, and non-manual markers. The proposed system integrates computer vision-based feature extraction, machine learning-assisted annotation, and a structured database for lexical entries. The web-based platform enables lexicographers to collect, annotate, and validate sign language entries efficiently. Evaluation with 35 participants, including lexicography experts, BdSL linguists, and deaf community members, showed a 67 % reduction in annotation time while maintaining high inter-annotator agreement
(κ = 0.82). During a six-month period, participants documented 1,847 BdSL signs, identified 127 regional variants, and created 456 dictionary records at different stages of completion. These records included entries containing core phonological annotations as well as entries that had undergone additional linguistic and expert validation, providing a foundation for the development of a future learner-facing dictionary for Bengali students with hearing impairments. The scientific novelty lies in applying automated methods specifically to BdSL lexicography and establishing foundational tools for systematic dictionary development.
1. Ashrafi A., Mokhnachev V.S. An information-theoretic metric for automated lexicographic selection in Bengali Sign Language. Modeling, Optimization and Information Technology. 2026;14(6). https://doi.org/10.26102/2310-6018/2026.57.6.011
2. Johnston T. Language standardization and signed language dictionaries. Sign Language Studies. 2003;3(4):431–468. https://doi.org/10.1353/sls.2003.0012
3. Mahmood N.T., Jabbar M.S., Abdalrazak M. A Real-Time Hand Gesture Recognition Based on Media-Pipe and Support Vector Machine. In: Advances in Intelligent Computing Techniques and Applications (IRICT 2023): Intelligent Systems, Intelligent Health Informatics, Intelligent Big Data Analytics and Smart Computing: Volume 2, 27–28 December 2023, Johor, Malaysia. Cham: Springer; 2024. P. 263–273. https://doi.org/10.1007/978-3-031-59707-7_23
4. Crasborn O., Zwitserlood I. The Corpus NGT: an online corpus for professionals and laymen. In: Proceedings of the 3rd Workshop on the Representation and Processing of Sign Languages, Marrakesh, Morocco. Paris: ELRA; 2008. P. 44–49.
5. Johnston T. From archive to corpus: Transcription and annotation in the creation of signed language corpora. International Journal of Corpus Linguistics. 2010;15(1):106–131. https://doi.org/10.1075/ijcl.15.1.05joh
6. Nardone M. Introduction to RESTful APIs. In: Secure RESTful APIs: Simple Solutions for Beginners. Berkeley: Apress; 2025. P. 1–13. https://doi.org/10.1007/979-8-8688-1285-9_1
7. Li M., Gao Q., Yu T. Kappa statistic considerations in evaluating inter-rater reliability between two raters: which, when and context matters. BMC Cancer. 2023;23(1):799. https://doi.org/10.1186/s12885-023-11325-z
8. Lakens D. Calculating and reporting effect sizes to facilitate cumulative science: a practical primer for t-tests and ANOVAs. Frontiers in Psychology. 2013;4:863. https://doi.org/10.3389/fpsyg.2013.00863
9. Ashrafi A., Mokhnachev V.S., Chung D.H., Makhmud A., Bacha W. Multilingual Sign Language Dictionary Development for Clinical Use. In: 2025 7th International Youth Conference on Radio Electronics, Electrical and Power Engineering (REEPE), 08–10 April 2025, Moscow, Russia. IEEE; 2025. https://doi.org/10.1109/REEPE63962.2025.10970922
10. Montgomery D.C., Peck E.A., Vining G.G. Introduction to Linear Regression Analysis. Hoboken: John Wiley & Sons; 2021. 704 p.
11. Finlayson M.A., Erjavec T. Overview of Annotation Creation: Processes and Tools. In: Handbook of Linguistic Annotation. Dordrecht: Springer; 2017. P. 167–191. https://doi.org/10.1007/978-94-024-0881-2_5
12. Kordia A.H., Melo F.S. Compound Movement Recognition Using Dynamic Movement Primitives. In: Progress in Artificial Intelligence: 20th EPIA Conference on Artificial Intelligence (EPIA 2021), 07–09 September 2021, Virtual Event. Cham: Springer; 2021. P. 456–468. https://doi.org/10.1007/978-3-030-86230-5_36
13. Caselli N.K., Sehyr Z.S., Cohen-Goldberg A.M., Emmorey K. ASL-LEX: A lexical database of American Sign Language. Behavior Research Methods. 2017;49(2):784–801. https://doi.org/10.3758/s13428-016-0742-0
14. Johnston T., Schembri A. Australian Sign Language (Auslan): An Introduction to Sign Language Linguistics. New York: Cambridge University Press; 2007. 332 p. https://doi.org/10.1017/CBO9780511607479
15. Hanke Th., König L., Wagner S., Matthes S. DGS Corpus & Dicta-Sign: The Hamburg Studio Setup. In: Corpora and Sign Language Technologies: Proceedings of the 4th Workshop on the Representation and Processing of Sign Languages: 7th International Conference on Language Resources and Evaluation, 17–23 May 2010, Valletta, Malta. ELRA; 2010. P. 106–109.
